@conference{cosmo2024,

title = {Constraint-Free Structure Learning with Smooth Acyclic Orientations},

author = {Martina Cinquini Francesco Landolfi Riccardo Massidda},

url = {https://openreview.net/forum?id=KWO8LSUC5W},

year  = {2024},

date = {2024-05-06},

urldate = {2024-01-01},

booktitle = {The Twelfth International Conference on Learning Representations},

abstract = {The structure learning problem consists of fitting data generated by a Directed Acyclic Graph (DAG) to correctly reconstruct its arcs. In this context, differentiable approaches constrain or regularize an optimization problem with a continuous relaxation of the acyclicity property. The computational cost of evaluating graph acyclicity is cubic on the number of nodes and significantly affects scalability. In this paper, we introduce COSMO, a constraint-free continuous optimization scheme for acyclic structure learning. At the core of our method lies a novel differentiable approximation of an orientation matrix parameterized by a single priority vector. Differently from previous works, our parameterization fits a smooth orientation matrix and the resulting acyclic adjacency matrix without evaluating acyclicity at any step. Despite this absence, we prove that COSMO always converges to an acyclic solution. In addition to being asymptotically faster, our empirical analysis highlights how COSMO performance on graph reconstruction compares favorably with competing structure learning methods.

},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bacciu2023c,

title = {Graph Representation Learning },

author = {Davide Bacciu and Federico Errica and Alessio Micheli and Nicolò Navarin and Luca Pasa and Marco Podda and Daniele Zambon



},

editor = {Michel Verleysen},

year  = {2023},

date = {2023-10-04},

urldate = {2023-10-04},

booktitle = {Proceedings of the 31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bacciu2023,

title = {Generalizing Downsampling from Regular Data to Graphs},

author = {Davide Bacciu and Alessio Conte and Francesco Landolfi},

url = {https://arxiv.org/abs/2208.03523, Arxiv},

year  = {2023},

date = {2023-02-07},

urldate = {2023-02-07},

booktitle = {Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence},

abstract = {Downsampling produces coarsened, multi-resolution representations of data and it is used, for example, to produce lossy compression and visualization of large images, reduce computational costs, and boost deep neural representation learning. Unfortunately, due to their lack of a regular structure, there is still no consensus on how downsampling should apply to graphs and linked data. Indeed reductions in graph data are still needed for the goals described above, but reduction mechanisms do not have the same focus on preserving topological structures and properties, while allowing for resolution-tuning, as is the case in regular data downsampling. In this paper, we take a step in this direction, introducing a unifying interpretation of downsampling in regular and graph data. In particular, we define a graph coarsening mechanism which is a graph-structured counterpart of controllable equispaced coarsening mechanisms in regular data. We prove theoretical guarantees for distortion bounds on path lengths, as well as the ability to preserve key topological properties in the coarsened graphs. We leverage these concepts to define a graph pooling mechanism that we empirically assess in graph classification tasks, providing a greedy algorithm that allows efficient parallel implementation on GPUs, and showing that it compares favorably against pooling methods in literature. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Massidda2022,

title = {Knowledge-Driven Interpretation of Convolutional Neural Networks},

author = {Riccardo Massidda and Davide Bacciu},

year  = {2022},

date = {2022-09-20},

urldate = {2022-09-20},

booktitle = {Proceedings of the 2022 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2022)},

abstract = {Since the widespread adoption of deep learning solutions in critical environments, the interpretation of artificial neural networks has become a significant issue. To this end, numerous approaches currently try to align human-level concepts with the activation patterns of artificial neurons. Nonetheless, they often understate two related aspects: the distributed nature of neural representations and the semantic relations between concepts. We explicitly tackled this interrelatedness by defining a novel semantic alignment framework to align distributed activation patterns and structured knowledge. In particular, we detailed a solution to assign to both neurons and their linear combinations one or more concepts from the WordNet semantic network. Acknowledging semantic links also enabled the clustering of neurons into semantically rich and meaningful neural circuits. Our empirical analysis of popular convolutional networks for image classification found evidence of the emergence of such neural circuits. Finally, we discovered neurons in neural circuits to be pivotal for the network to perform effectively on semantically related tasks. We also contribute by releasing the code that implements our alignment framework.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {The Infinite Contextual Graph Markov Model},

author = {Daniele Castellana and Federico Errica and Davide Bacciu and Alessio Micheli

},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

booktitle = {Proceedings of the 39th International Conference on Machine Learning (ICML 2022)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bacciu2021c,

title = { Deep learning for graphs},

author = {Davide Bacciu and Filippo Maria Bianchi and Benjamin Paassen and Cesare Alippi},

editor = {Michel Verleysen},

doi = {10.14428/esann/2021.ES2021-5},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)},

pages = {89-98},

abstract = { Deep learning for graphs encompasses all those models endowed with multiple layers of abstraction, which operate on data represented as graphs. The most common building blocks of these models are graph encoding layers, which compute a vector embedding for each node in a graph based on a sum of messages received from its neighbors. However, the family also includes architectures with decoders from vectors to graphs and models that process time-varying graphs and hypergraphs. In this paper, we provide an overview of the key concepts in the field, point towards open questions, and frame the contributions of the ESANN 2021 special session into the broader context of deep learning for graphs. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Dukic2021,

title = {Inductive learning for product assortment graph completion},

author = {Haris Dukic and Georgios Deligiorgis and Pierpaolo Sepe and Davide Bacciu and Marco Trincavelli},

editor = {Michel Verleysen},

doi = {10.14428/esann/2021.ES2021-73},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)},

pages = {129-134},

abstract = { Global retailers have assortments that contain hundreds of thousands of products that can be linked by several types of relationships like style compatibility, "bought together", "watched together", etc. Graphs are a natural representation for assortments, where products are nodes and relations are edges. Relations like style compatibility are often produced by a manual process and therefore do not cover uniformly the whole graph. We propose to use inductive learning to enhance a graph encoding style compatibility of a fashion assortment, leveraging rich node information comprising textual descriptions and visual data. Then, we show how the proposed graph enhancement improves substantially the performance on transductive tasks with a minor impact on graph sparsity. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Numeroso2021,

title = {MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks},

author = {Danilo Numeroso and Davide Bacciu},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{BacciuPoddaIJCNN2021,

title = {GraphGen-Redux: a Fast and Lightweight Recurrent Model for Labeled Graph Generation},

author = {Davide Bacciu and Marco Podda},

doi = {10.1109/IJCNN52387.2021.9533743},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

organization = {IEEE},

abstract = {The problem of labeled graph generation is gaining attention in the Deep Learning community. The task is challenging due to the sparse and discrete nature of graph spaces. Several approaches have been proposed in the literature, most of which require to transform the graphs into sequences that encode their structure and labels and to learn the distribution of such sequences through an auto-regressive generative model. Among this family of approaches, we focus on the Graphgen model. The preprocessing phase of Graphgen transforms graphs into unique edge sequences called Depth-First Search (DFS) codes, such that two isomorphic graphs are assigned the same DFS code. Each element of a DFS code is associated with a graph edge: specifically, it is a quintuple comprising one node identifier for each of the two endpoints, their node labels, and the edge label. Graphgen learns to generate such sequences auto-regressively and models the probability of each component of the quintuple independently. While effective, the independence assumption made by the model is too loose to capture the complex label dependencies of real-world graphs precisely. By introducing a novel graph preprocessing approach, we are able to process the labeling information of both nodes and edges jointly. The corresponding model, which we term Graphgen-redux, improves upon the generative performances of Graphgen in a wide range of datasets of chemical and social graphs. In addition, it uses approximately 78% fewer parameters than the vanilla variant and requires 50% fewer epochs of training on average.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Errica2021,

title = {Graph Mixture Density Networks},

author = {Federico Errica and Davide Bacciu and Alessio Micheli},

url = {https://proceedings.mlr.press/v139/errica21a.html, PDF},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML 2021)},

pages = {3025-3035},

publisher = {PMLR},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sattar2021,

title = {Context-aware Graph Convolutional Autoencoder},

author = {Asma Sattar and Davide Bacciu

},

doi = {10.1007/978-3-030-85030-2_23},

year  = {2021},

date = {2021-06-16},

urldate = {2021-06-16},

booktitle = {Proceedings of the 16th International Work Conference on Artificial Neural Networks (IWANN 2021)},

volume = {12862},

pages = { 279-290},

publisher = {Springer},

series = {LNCS},

abstract = {Recommendation problems can be addressed as link prediction tasks in a bipartite graph between user and item nodes, labelled with rating on edges. Existing matrix completion approaches model the user’s opinion on items by ignoring context information that can instead be associated with the edges of the bipartite graph. Context is an important factor to be considered as it heavily affects opinions and preferences. Following this line of research, this paper proposes a graph convolutional auto-encoder approach which considers users’ opinion on items as well as the static node features and context information on edges. Our graph encoder produces a representation of users and items from the perspective of context, static features, and rating opinion. The empirical analysis on three real-world datasets shows that the proposed approach outperforms recent state-of-the-art recommendation systems.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{aistats2020,

title = {A Deep Generative Model for Fragment-Based Molecule Generation},

author = {Marco Podda and Davide Bacciu and Alessio Micheli},

url = {https://arxiv.org/abs/2002.12826},

year  = {2020},

date = {2020-06-03},

urldate = {2020-06-03},

booktitle = {Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020) },

abstract = {Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular graphs as strings of text, and learn their corresponding character-based language model. Another, more expressive, approach operates directly on the molecular graph. In this work, we address two limitations of the former: generation of invalid or duplicate molecules. To improve validity rates, we develop a language model for small molecular substructures called fragments, loosely inspired by the well-known paradigm of Fragment-Based Drug Design. In other words, we generate molecules fragment by fragment, instead of atom by atom. To improve uniqueness rates, we present a frequency-based clustering strategy that helps to generate molecules with infrequent fragments. We show experimentally that our model largely outperforms other language model-based competitors, reaching state-of-the-art performances typical of graph-based approaches. Moreover, generated molecules display molecular properties similar to those in the training sample, even in absence of explicit task-specific supervision.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{iclr19,

title = {A Fair Comparison of Graph Neural Networks for Graph Classification},

author = {Federico Errica and Marco Podda and Davide Bacciu and Alessio Micheli},

url = {https://openreview.net/pdf?id=HygDF6NFPB, PDF

https://iclr.cc/virtual_2020/poster_HygDF6NFPB.html, Talk

https://github.com/diningphil/gnn-comparison, Code},

year  = {2020},

date = {2020-04-30},

booktitle = {Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)},

abstract = {Experimental reproducibility and replicability are critical topics in machine learning. Authors have often raised concerns about their lack in scientific publications to improve the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works.

As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures often lack rigorousness and are hardly reproducible. Motivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art. To counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks. Moreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet. We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{aiia2019,

title = {A non-negative factorization approach to node pooling in graph convolutional neural networks},

author = {Davide Bacciu and Luigi {Di Sotto}},

url = {https://arxiv.org/pdf/1909.03287.pdf},

year  = {2019},

date = {2019-11-22},

booktitle = {Proceedings of the 18th International Conference of the Italian Association for Artificial Intelligence (AIIA 2019)},

publisher = {Springer-Verlag},

series = {Lecture Notes in Artificial Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{esann19GraphGen,

title = {Graph generation by sequential edge prediction},

author = {Davide Bacciu and Alessio Micheli and Marco Podda},

editor = {Michel Verleysen},

url = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-107.pdf},

year  = {2019},

date = {2019-04-24},

booktitle = {Proceedings  of the European Symposium on Artificial Neural Networks,  Computational Intelligence and Machine Learning (ESANN'19)},

publisher = {i6doc.com},

address = {Louvain-la-Neuve, Belgium},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{icml2018,

title = {Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing},

author = {Bacciu Davide and Errica Federico and Micheli Alessio},

url = {https://arxiv.org/abs/1805.10636},

year  = {2018},

date = {2018-07-11},

urldate = {2018-07-11},

booktitle = {Proceedings of the 35th International Conference on Machine Learning (ICML 2018)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}